Lp3
Medium
- Category
- MCP Least Privilege
- Confidence
- 90% confidence
- Finding
- The skill advertises use of environment variables and shell-based execution patterns, but it does not declare permissions or capabilities explicitly. That creates a transparency and governance gap: an agent or reviewer may not realize the skill can access secrets or invoke commands, which increases the chance of unsafe execution, secret exposure, or unintended side effects in environments that rely on declared permissions for policy enforcement.
